Functional Link Artificial Neural Network Model Research Articles

Pan evaporation modeling in different agroclimatic zones using functional link artificial neural network

Pan evaporation is an important climatic variable for developing efficient water resource management strategies. In the past, many machine learning models are reported in the literature for pan evaporation modeling using the different combinationof available climatic variables. In order to develop a novel model with improved accuracy and reduced computational complexity, the functional link artificial neural network (FLANN) is chosen as an architecture to estimate daily pan evaporation in three agro-climatic zones (ACZs) of Chhattisgarh state in east-central India. Single neuron and single layer in its structure make it less complex as compared to other multilayer neural networks and neuro-fuzzy based hybrid models. Estimation results obtained with the FLANN model are compared with those obtained by multi-layer artificial neural networks (MLANN) and two empirical methods using the same raw data and corresponding features. Statistical indices like root mean square error (RMSE), mean absolute error (MAE) and efficiency factor (EF) is also computed to evaluate the model performance. It is demonstrated that pan evaporation estimates obtained with the proposed FLANN models provide an improved estimation of pan evaporation (RMSE = 0.85 to 1.27 mmd-1, MAE = 0.63 to 0.95 mmd-1 and EF = 0.70 to 0.89) as compared to MLANN (RMSE = 0.94 to 1.58 mmd-1, MAE = 0.73 to 1.14 mmd-1 and EF = 0.62 to 0.88) and empirical (RMSE = 1.19 to 2.19 mmd-1, MAE = 0.91 to 1.62 mmd-1 and EF = 0.49 to 0.88) models in different ACZs.

An improved harmony search-based functional link higher order ANN for nonlinear data classification

To obtain the optimal set of weights in any higher order artificial neural network, it is often laborious to adjust the set of weights by using appropriate learning algorithm. In this paper, an improved variant of harmony search (HS), called improved harmony search (IHS) along with gradient descent learning (GDL) is used with functional link artificial neural network (FLANN) for the task of classification in data mining. IHS performs better than HS by eliminating constant parameters [bandwidth (bw), pitch adjustment rate (PAR)] in HS algorithm and incorporating changes dynamically in PAR and bw with iteration. The searching capability of IHS to obtain optimal harmony is used along with GDL to discover optimal set of weights for FLANN model. The proposed IHS-GDL-FLANN is implemented in MATLAB and compared with other alternatives. In order to get statistical correctness of results, the proposed method is analysed by using various statistical analysis under null-hypothesis.

A novel robust regression model based on functional link least square (FLLS) and its application to modeling complex chemical processes

In this paper, a novel robust regression model is proposed. The proposed robust regression model is called functional link least square (FLLS). The idea of the proposed FLLS model arises from the functional link artificial neural network (FLANN). The FLANN model can be established by using the Error Back-propagation algorithm. However, the performance of the FLANN model is limited. Different from the FLANN model, the proposed FLLS model can achieve an optimal regression model by using the least square algorithm. The proposed FLLS model has some salient features: first, the algorithm of FLLS is extremely fast; secondly, the training errors of the FLLS model can be nearly minimized to be zero; third, the testing performance of FLLS model is robust. In order to evaluate the performance of the proposed regression model, case studies of modeling two complex chemical processes are provided. Two more models of the FLANN and the partial least square (PLSR) are also developed for comparisons. Results illustrated that the proposed FLLS regression model could significantly improve the testing performance.

A Meta-heuristic Framework for Secondary Protein Structure Prediction using BAT-FLANN Optimization Algorithm

Background/Objectives: Proteins are the fundamental units of biology; the mechanism by which primary sequence of proteins is predicted into its secondary structure is not yet accurately achieved. Methods/Statistical analysis: In this paper, BAT inspired FLANN (Functional Link Artificial Neural Network) model for protein secondary structure prediction with low computation cost and accuracy has been proposed. The proposed model consists of three different phases; i) First, the primary sequence of amino acid is converted into dynamic matrix for different window sizes then this dynamic matrix is used to derive correlation matrix, ii) Second, FLANN is used to classify each sequence of correlation matrix with different learning parameters and random weights. BAT inspired optimization algorithm has been used to optimize the weight and learning parameters of BAT-FLANN, and (iii) finally, refinement of secondary structure result. Results: Experiments were conducted with real datasets of some primary sequence on RS126 and CB396 datasets. Proposed method has been compared with existing DSC, NNSSP, PHD, PREDATOR, ZPRED, MULPRED, SVM models and found to be more promising. Conclusion/Application: The proposed method achieves average Q3 accuracy 81.2% and 82.7% for CB396 and RS126 dataset respectively. Moreover the segment overlap (SOV) is 76.1% and 75.3% for CB396 and RS126 dataset respectively.

A self-adaptive fuzzy-based optimised functional link artificial neural network model for financial time series prediction

In recent years, new data mining and machine learning techniques have been developed and applied to various fields of science. Out of these recently developed techniques few offer online support and are able to adapt to large and complex financial dataset. Therefore, the present research adopts Functional Link Artificial Neural Network (FLANN) model for predicting the closing price of three companies namely Yahoo Inc, Nokia and Bank of America. The FLANN model used is trained by fuzzy after normalisation of the data and closing price is forecasted for one day and one week ahead. The prediction result is compared with the parameters of the FLANN model trained by Genetic Algorithm (GA) and Particle Swarm Optimisation (PSO). The proposed training method provides better accuracy and takes less time as compared to training the FLANN model using PSO or GA. The proposed approach has also been compared with a linear dataset for validation. The FLANN-fuzzy approach is seen to provide better results in predicting financial distress.

A harmony search-based artificial neural network for stock market prediction

For financial time series, the generation of error bars on the point prediction is important in order to estimate the corresponding risk. In recent years, artificial intelligence optimisation techniques have been used to make time series approaches more systematic and improve forecasting performance. The harmony search learning methodology, already successfully applied for training of multilayer perceptrons, is applied to Functional Link Artificial Neural Network (FLANN) in order to infer non-linear models for predicting a time series and the related volatility. The proposed method is implemented and the results are compared with FLANN model trained by back propagation and differential evolution. The proposed training method shows that FLANN-harmony search provides better forecasting/prediction as compared to training the FLANN model using back propagation or differential evolution.

A hybrid Evolutionary Functional Link Artificial Neural Network for Data mining and Classification

This paper presents a specific structure of neural network as the functional link artificial neural network (FLANN). This technique has been employed for classification tasks of data mining. In fact, there are a few studies that used this tool for solving classification problems. In this present research, we propose a hybrid FLANN (HFLANN) model, where the optimization process is performed using 3 known population based techniques such as genetic algorithms, particle swarm and differential evolution. This model will be empirically compared to FLANN based back-propagation algorithm and to others classifiers as decision tree, multilayer perceptron based back-propagation algorithm, radical basic function, support vector machine, and K-nearest Neighbor. Our results proved that the proposed model outperforms the other single model. (Abstract)

Application of Functional Link Artificial Neural Network for Prediction of Machinery Noise in Opencast Mines

Functional link-based neural network models were applied to predict opencast mining machineries noise. The paper analyzes the prediction capabilities of functional link neural network based noise prediction models vis-à-vis existing statistical models. In order to find the actual noise status in opencast mines, some of the popular noise prediction models, for example, ISO-9613-2, CONCAWE, VDI, and ENM, have been applied in mining and allied industries to predict the machineries noise by considering various attenuation factors. Functional link artificial neural network (FLANN), polynomial perceptron network (PPN), and Legendre neural network (LeNN) were used to predict the machinery noise in opencast mines. The case study is based on data collected from an opencast coal mine of Orissa, India. From the present investigations, it could be concluded that the FLANN model give better noise prediction than the PPN and LeNN model.

Development and performance evaluation of FLANN based model for forecasting of stock markets

A trigonometric functional link artificial neural network (FLANN) model for short (one day) as well as long term (one month, two months) prediction of stock price of leading stock market indices: DJIA and S&P 500 is developed in this paper. The proposed FLANN model employs the least mean square (LMS) as well as the recursive least square (RLS) algorithms in different experiments to train the weights of the model. The historical index data transformed into various technical indicators as well as macro economic data as fundamental factors are considered as inputs to the proposed models. The mean absolute percentage error (MAPE) with respect to actual stock prices is selected as the performance index to gauge the quality of prediction of the models. Extensive simulation and test results show that the application of FLANN to the stock market prediction problem gives out results which are comparable to other neural network models. In addition the proposed models are structurally simple and requires less computation during training and testing as the model contains only one neuron and one layer. Between the two models proposed the FLANN–RLS requires substantially less experiments to train compared to the LMS based model. This feature makes the RLS-based FLANN model more suitable for online prediction.